4009week4lecture

Ame Liu 22910358

1.pairs 矩阵散点图 探索两两变量之间的相关性

rw <-read.table('/Users/liuyu/Downloads/winequality-red.csv', head=T,sep=',',fileEncoding = 'UTF-8')
pairs(rw)

pairs(~pH+alcohol+quality+density, data=rw)

只显示下半边数据

pairs(~pH+alcohol+quality+density, data=rw,upper.panel = NULL)

绘制mpg图像

a <- data.frame(mpg)
pairs(~displ+cty+hwy, data=mpg)# mpg是ggplot2的内置数据集

绘制散点图，封装散点图(具体到每一个类)，对比图

library(ggplot2)
summary(mpg$displ)#mpg的displ数据

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  1.600   2.400   3.300   3.472   4.600   7.000 

ggplot(iris,aes(Sepal.Length,Sepal.Width))+geom_point()+facet_wrap(~Species)#作iris数据集的图

#针对iris数据库进行关于Species的分面处理
ggplot(mpg,aes(displ,hwy))+geom_point(colour='blue')+facet_wrap(~class,ncol = 2)+labs(title = "point geom")#aes是设置横纵坐标,facet_wrap此处为封装型，geom_point()是绘制散点图,tile是设置标题.

ggplot(mpg,aes(displ,hwy))+geom_point(colour='blue')+labs(title = "point geom")#点状图

ggplot(mpg,aes(displ,hwy))+geom_smooth(colour='yellow')+labs(title = "geom_smooth")#平滑图

`geom_smooth()` using method = 'loess' and formula 'y ~ x'

#通过gridExtra做对比图
p1 <- ggplot(mpg,aes(displ,hwy))+geom_point(colour='blue')+facet_wrap(~class)+labs(title = "point geom")

p2 <- ggplot(mpg,aes(displ,hwy))+geom_smooth(colour='yellow')+labs(title = "geom_smooth")

library(gridExtra)
grid.arrange(p1, p2, ncol=2)

`geom_smooth()` using method = 'loess' and formula 'y ~ x'

展示一下mpg和iris内置数据集，是流行的车的数据

rrr <- data.frame(mpg)
rrr

mm <- data.frame(iris)
mm

Aesthetic levels

ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy, size = class), show.legend = TRUE)

d<- ggplot(mpg,aes(x=displ,y=hwy,size = class))+geom_point(fill = "red",show.legend = TRUE)+labs(title = "point geom") #geom_point1
c <- ggplot(mpg,aes(x=displ,y=hwy,shape = drv,alpha = class))+geom_point(colour='black',fill = "red")+labs(title = "point geom")   #geom_point2

a <- ggplot(mpg,aes(x=displ,y=hwy,group = drv))+geom_smooth(colour='yellow')+labs(title = "geom_smooth")
#geom_smooth1
b <- ggplot(mpg,aes(x=displ,y=hwy,color = drv,linetype = drv))+geom_smooth(colour='yellow')+labs(title = "geom_smooth") #geom_smooth2
grid.arrange(a, b,c, d, ncol=2)

library(gridExtra)
p1 <- ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, group = drv)) #mapping意为映射
p2 <- ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, color = drv,
linetype = drv))
p3 <- ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy, size = class),
show.legend = TRUE) #显示图例标注
p4 <- ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy, alpha = class,
shape = drv))
grid.arrange(p1, p2, p3, p4, ncol=2)

`geom_smooth()` using method = 'loess' and formula 'y ~ x'
`geom_smooth()` using method = 'loess' and formula 'y ~ x'
Warning: Using size for a discrete variable is not advised.
Warning: Using alpha for a discrete variable is not advised.

ggplot(mpg,aes(x = displ, y = hwy))+geom_point()+geom_smooth()

`geom_smooth()` using method = 'loess' and formula 'y ~ x'

#作图（数据，坐标）+ 选择图形种类
ggplot(mpg,aes(x=displ,y=hwy,color=class))+geom_point()+geom_smooth()

`geom_smooth()` using method = 'loess' and formula 'y ~ x'
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  span too small.   fewer data values than degrees of freedom.
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  pseudoinverse used at 5.6935
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  neighborhood radius 0.5065
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  reciprocal condition number  0
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  There are other near singularities as well. 0.65044
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  span too small.   fewer data values than degrees of freedom.
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  pseudoinverse used at 5.6935
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  neighborhood radius 0.5065
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  reciprocal condition number  0
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  There are other near singularities as well. 0.65044
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  pseudoinverse used at 4.008
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  neighborhood radius 0.708
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  reciprocal condition number  0
Warning in simpleLoess(y, x, w, span, degree = degree, parametric = parametric,  :
  There are other near singularities as well. 0.25
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  pseudoinverse used at 4.008
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  neighborhood radius 0.708
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  reciprocal condition number  0
Warning in predLoess(object$y, object$x, newx = if (is.null(newdata)) object$x else if (is.data.frame(newdata)) as.matrix(model.frame(delete.response(terms(object)),  :
  There are other near singularities as well. 0.25

Hexbin - 2D histogram geom_hex()为六边形散点图

library(hexbin)
a1 <- with(rw,{bin<-hexbin(x=pH,y=density,xbins=10) #xbins的意思为x即是个数，以10个位一组计数
             plot(bin)})

ggplot(rw,aes(pH,density))+geom_smooth(colour='yellow')+labs(title = "geom_smooth")+geom_hex()

`geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'

ggplot2之常见观察变量绘图geom https://www.jianshu.com/p/4e4f6168fa37

反映频率的图(适合整数)：

ggplot(data = rw) +
geom_count(mapping = aes(x=pH, y=density))

近似热图

library(dplyr)
counting <- count(mpg, displ, hwy)
ggplot(counting,aes(displ,hwy)) +
geom_tile(mapping = aes(fill = n))#设n为数量